© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen2.5-7B-IT
    5. 20-MATRYOSHKA-65K
    7. 2039
    Prev
    Next
    INDEX
    Explanations

    code comments

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/qwen2.5-7B-it-layer-20-saes/pile/matryoshka/k-100
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    macen
    -0.22
    æľ¨åľ°æĿ¿
    -0.21
    /*↵
    -0.21
    лÑıÑĢ
    -0.20
    ASM
    -0.20
    ksam
    -0.20
    .Yellow
    -0.20
    forgettable
    -0.19
    lassian
    -0.19
    bote
    -0.19
    POSITIVE LOGITS
     */↵↵↵↵
    0.21
     ((__
    0.20
     (~(
    0.20
     antlr
    0.19
     strokeLine
    0.19
     Shorts
    0.18
    çĶ¾
    0.18
    	Copyright
    0.18
    æĺŁåº§
    0.18
    chandle
    0.18
    Activations Density 0.006%

    No Known Activations